Measuring psychological stress from cardiovascular and activity signals

Abstract

A method and system for measuring psychological stress disclosed. In a first aspect, the method comprises determining R-R intervals from an electrocardiogram (ECG) to calculate a standard deviation of the R-R intervals (SDNN) and determining a stress feature (SF) using the SDNN. In response to reaching a threshold, the method includes performing adaptation to update a probability mass function (PMF). The method includes determining a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress. In a second aspect, the system comprises a wireless sensor device coupled to a user via at least one electrode, wherein the wireless sensor device includes a processor and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to carry out the steps of the method.

What is claimed is: 
     
       1. A system for measuring psychological stress, the system comprising:
 a wireless sensor device coupled to a user via at least one electrode to measure an electrocardiogram (ECG), wherein the wireless sensor device includes a processor; and 
 a memory device coupled to the processor, wherein the memory device stores an application that in response to execution by the processor, causes the processor to:
 determine R-R intervals from the ECG to calculate a standard deviation of the R-R intervals (SDNN); 
 determine a stress feature (SF) using the SDNN by:
 calculating a mean heart rate (HR) from the ECG within the predetermined time period, and 
 calculating the SF utilizing an algorithm SF=HR+α*SDNN, wherein α is predetermined negative variable that allows for combining HR and SDNN; 
 
 in response to reaching a threshold, perform adaptation to update a probability mass function (PMF), comprising:
 grouping data into a predetermined distribution, 
 calibrating the predetermined distribution according to a detected resting heart rate, and 
 adjusting the predetermined distribution according to additional samples received; and 
 
 
 determine a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress. 
 
     
     
       2. The system of  claim 1 , wherein the application further causes the processor to:
 determine a posture state, wherein the psychological stress is not measured if the posture state is active; and 
 display the determined SL to a user or another device. 
 
     
     
       3. The system of  claim 2 , wherein the posture state includes any of active, sitting, and standing. 
     
     
       4. The system of  claim 1 , wherein the determine the R-R intervals from the ECG to calculate the SDNN, comprises:
 detect R peaks from a measured ECG within the predetermined time period; and 
 calculate R-R intervals using the detected R peaks. 
 
     
     
       5. The system of  claim 1 , wherein the adjusting the predetermined distribution according to the additional samples received comprises:
 in response to data arriving, multiply all bins of the predetermined distribution by 1-ε, wherein ε is a parameter for how much the PMF is changed with each adaptation; and 
 add £ to a bin corresponding to the data. 
 
     
     
       6. The system of  claim 1 , wherein the determine the SL using the SF and the PMF, comprises:
 add all bins below a bin corresponding to the SF; and 
 compute the SL utilizing an algorithm that includes a probability mass function for a given posture (PMF posture ), the SF, and the added bins. 
 
     
     
       7. The system of  claim 6 , wherein the application further causes the processor to:
 add a fraction of a current bin to improve granularity. 
 
     
     
       8. A wireless sensor device to measure psychological stress, comprising:
 at least one electrode coupled to a user to measure an electrocardiogram (ECG) of the user; and 
 a memory device coupled to a processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to:
 determine R-R intervals from the ECG to calculate a standard deviation of the R-R intervals (SDNN); 
 determine a stress feature (SF) using the SDNN; 
 in response to reaching a threshold, perform adaptation to update a probability mass function (PMF), comprising:
 grouping data into a predetermined distribution, 
 calibrating the predetermined distribution according to a detected resting heart rate, and 
 adjusting the predetermined distribution according to additional samples received by:
 in response to data arriving, multiply all bins of the predetermined distribution by 1-ε, wherein ε is a parameter for how much the PMF is changed with each adaptation; and 
 add ε to a bin corresponding to the data; and 
 
 
 
 determine a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress. 
 
     
     
       9. The wireless sensor device of  claim 8 , wherein the application further causes the processor to:
 determine a posture state, wherein the psychological stress is not measured if the posture state is active; and 
 display the determined SL to a user or another device. 
 
     
     
       10. The wireless sensor device of  claim 9 , wherein the posture state includes any of active, sitting, and standing. 
     
     
       11. The wireless sensor device of  claim 8 , wherein the determine R-R intervals from the ECG to calculate the SDNN, comprises:
 detect R peaks from a measured ECG within the predetermined time period; and 
 calculate R-R intervals using the detected R peaks. 
 
     
     
       12. The wireless sensor device of  claim 8 , wherein the determine the stress feature (SF) using the SDNN comprises:
 calculate a mean heart rate (HR) from the ECG within the predetermined time period; and 
 calculate the SF utilizing an algorithm SF=HR+a*SDNN, wherein a is predetermined negative variable that allows for combining HR and SDNN. 
 
     
     
       13. The wireless sensor device of  claim 8 , wherein the determine the SL using the SF and the PMF, comprises:
 add all bins below a bin corresponding to the SF; and 
 compute the SL utilizing an algorithm that includes a probability mass function for a given posture (PMF posture ), the SF, and the added bins. 
 
     
     
       14. The wireless sensor device of  claim 8 , wherein the application further causes the processor to:
 add a fraction of a current bin to improve granularity. 
 
     
     
       15. A non-transitory computer-readable medium storing executable instructions that, in response to execution, cause a wireless sensor device to perform operations comprising:
 determining R-R intervals from the ECG to calculate a standard deviation of the R-R intervals (SDNN); 
 determining a stress feature (SF) using the SDNN; 
 in response to reaching a threshold, performing adaptation to update a probability mass function (PMF), comprising: 
 grouping data into a predetermined distribution; 
 calibrating the predetermined distribution according to a detected resting heart rate; and 
 adjusting the predetermined distribution according to additional samples received; and 
 determine a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress by: 
 adding all bins below a bin corresponding to the SF, and 
 computing the SL utilizing an algorithm that includes a probability mass function for a given posture (PMF posture ), the SF, and the added bins. 
 
     
     
       16. A wireless sensor device to measure psychological stress, comprising:
 at least one electrode coupled to a user to measure an electrocardiogram (ECG) of the user; and 
 a memory device coupled to a processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to:
 determine R-R intervals from the ECG to calculate a standard deviation of the R-R intervals (SDNN); 
 determine a stress feature (SF) using the SDNN; 
 in response to reaching a threshold, perform adaptation to update a probability mass function (PMF), comprising:
 grouping data into a predetermined distribution, 
 calibrating the predetermined distribution according to a detected resting heart rate, and 
 adjusting the predetermined distribution according to additional samples received; 
 
 add a fraction of a current bin to improve granularity; and 
 determine a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress.